FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4306292327> ?p ?o ?g. }

• W4306292327 endingPage "649" @default.
• W4306292327 startingPage "639" @default.
• W4306292327 abstract "Data Science and Machine Learning (ML) techniques’ applications to the human microbiome data exhibited a potential to identify biomarkers and participate in the early diagnosis of several medical conditions. In this paper, we explored the application of ML to biological data from Alzheimer’s disease patients. We trained ten classification models that used fecal 16S rRNA sequence data to differentiate between subjects affected by Alzheimer’s disease (AD), pre-onset amnestic mild cognitive impairment patients (aMCI), and healthy controls (HC) (n = 93 patients, 33 AD, 32 aMCI, 28 HC). Before the classification process, bioinformatics analysis was performed using the QIIME2–2021.4 tool which resulted in profiling microbiome communities present in host organisms. Alpha diversity metrics were calculated using three different indexes (Shannon’s diversity index, Faith’s Phylogenetic Diversity, and Observed OTUs) while Kruskal–Wallis test was used to confirm significant difference (p-value < 0.05) between study groups. To achieve binary classification, the dataset was divided into three subsets each containing two groups (AD vs aMCI, AD vs HC, aMCI vs HC) Prior to the classification process, SelectKBest with the f_classif algorithm was used as univariate feature selection to reduce the number of features in each group to top five. 5-fold cross-validation yielded high accuracy results (going over 70%) for a number of classifiers, with the highest accuracy reach of 78.3% (via Logistic Regression) in the case of distinguishing between aMCI and HC subjects. Our results showed that a machine learning algorithm can be developed and achieve high precision (>78%) with relatively few parameters. Such a model can be used to support decision-making in medicine by gathering the data through a non-invasive technique." @default.
• W4306292327 created "2022-10-15" @default.
• W4306292327 creator A5015360346 @default.
• W4306292327 creator A5055359400 @default.
• W4306292327 creator A5064713642 @default.
• W4306292327 date "2022-10-16" @default.
• W4306292327 modified "2023-10-01" @default.
• W4306292327 title "Investigation of the Role of the Microbiome in the Development of Alzheimer’s Disease Using Machine Learning Techniques" @default.
• W4306292327 cites W1495556587 @default.
• W4306292327 cites W1570713908 @default.
• W4306292327 cites W2072970694 @default.
• W4306292327 cites W2103296919 @default.
• W4306292327 cites W2594389980 @default.
• W4306292327 cites W2616825195 @default.
• W4306292327 cites W2761210275 @default.
• W4306292327 cites W2762048636 @default.
• W4306292327 cites W2808457437 @default.
• W4306292327 cites W2890106926 @default.
• W4306292327 cites W2910455347 @default.
• W4306292327 cites W2912270772 @default.
• W4306292327 cites W2944415973 @default.
• W4306292327 cites W2944552216 @default.
• W4306292327 cites W2996431818 @default.
• W4306292327 cites W3008752724 @default.
• W4306292327 cites W3093405588 @default.
• W4306292327 cites W3132242954 @default.
• W4306292327 cites W3140172330 @default.
• W4306292327 cites W3157832516 @default.
• W4306292327 cites W3165179450 @default.
• W4306292327 cites W4206800544 @default.
• W4306292327 cites W4225524810 @default.
• W4306292327 cites W4232815266 @default.
• W4306292327 doi "https://doi.org/10.1007/978-3-031-17697-5_48" @default.
• W4306292327 hasPublicationYear "2022" @default.
• W4306292327 type Work @default.
• W4306292327 citedByCount "1" @default.
• W4306292327 countsByYear W43062923272023 @default.
• W4306292327 crossrefType "book-chapter" @default.
• W4306292327 hasAuthorship W4306292327A5015360346 @default.
• W4306292327 hasAuthorship W4306292327A5055359400 @default.
• W4306292327 hasAuthorship W4306292327A5064713642 @default.
• W4306292327 hasConcept C119857082 @default.
• W4306292327 hasConcept C126322002 @default.
• W4306292327 hasConcept C143121216 @default.
• W4306292327 hasConcept C148483581 @default.
• W4306292327 hasConcept C151956035 @default.
• W4306292327 hasConcept C153180895 @default.
• W4306292327 hasConcept C154945302 @default.
• W4306292327 hasConcept C161584116 @default.
• W4306292327 hasConcept C199163554 @default.
• W4306292327 hasConcept C2779134260 @default.
• W4306292327 hasConcept C41008148 @default.
• W4306292327 hasConcept C60644358 @default.
• W4306292327 hasConcept C71924100 @default.
• W4306292327 hasConcept C86803240 @default.
• W4306292327 hasConceptScore W4306292327C119857082 @default.
• W4306292327 hasConceptScore W4306292327C126322002 @default.
• W4306292327 hasConceptScore W4306292327C143121216 @default.
• W4306292327 hasConceptScore W4306292327C148483581 @default.
• W4306292327 hasConceptScore W4306292327C151956035 @default.
• W4306292327 hasConceptScore W4306292327C153180895 @default.
• W4306292327 hasConceptScore W4306292327C154945302 @default.
• W4306292327 hasConceptScore W4306292327C161584116 @default.
• W4306292327 hasConceptScore W4306292327C199163554 @default.
• W4306292327 hasConceptScore W4306292327C2779134260 @default.
• W4306292327 hasConceptScore W4306292327C41008148 @default.
• W4306292327 hasConceptScore W4306292327C60644358 @default.
• W4306292327 hasConceptScore W4306292327C71924100 @default.
• W4306292327 hasConceptScore W4306292327C86803240 @default.
• W4306292327 hasLocation W43062923271 @default.
• W4306292327 hasOpenAccess W4306292327 @default.
• W4306292327 hasPrimaryLocation W43062923271 @default.
• W4306292327 hasRelatedWork W1558995637 @default.
• W4306292327 hasRelatedWork W2093452304 @default.
• W4306292327 hasRelatedWork W2118578744 @default.
• W4306292327 hasRelatedWork W2325641712 @default.
• W4306292327 hasRelatedWork W2372905118 @default.
• W4306292327 hasRelatedWork W3138745612 @default.
• W4306292327 hasRelatedWork W4293525103 @default.
• W4306292327 hasRelatedWork W4312330541 @default.
• W4306292327 hasRelatedWork W4376607919 @default.
• W4306292327 hasRelatedWork W3123176164 @default.
• W4306292327 isParatext "false" @default.
• W4306292327 isRetracted "false" @default.
• W4306292327 workType "book-chapter" @default.